'use strict';
|
/**
|
* Copyright (c) 2017 Baidu.com, Inc. All Rights Reserved
|
*
|
* Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
|
* the License. You may obtain a copy of the License at
|
*
|
* http://www.apache.org/licenses/LICENSE-2.0
|
*
|
* Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
|
* an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
|
* specific language governing permissions and limitations under the License.
|
*
|
* @file AipNlp.js
|
* @author baidu aip
|
*/
|
|
const BaseClient = require('./client/baseClient');
|
|
const RequestInfo = require('./client/requestInfo');
|
|
const HttpClient = require('./http/httpClientNlp');
|
|
const objectTools = require('./util/objectTools');
|
|
const METHOD_POST = 'POST';
|
|
const LEXER_PATH = '/rpc/2.0/nlp/v1/lexer';
|
const LEXER_CUSTOM_PATH = '/rpc/2.0/nlp/v1/lexer_custom';
|
const DEP_PARSER_PATH = '/rpc/2.0/nlp/v1/depparser';
|
const WORD_EMBEDDING_PATH = '/rpc/2.0/nlp/v2/word_emb_vec';
|
const DNNLM_CN_PATH = '/rpc/2.0/nlp/v2/dnnlm_cn';
|
const WORD_SIM_EMBEDDING_PATH = '/rpc/2.0/nlp/v2/word_emb_sim';
|
const SIMNET_PATH = '/rpc/2.0/nlp/v2/simnet';
|
const COMMENT_TAG_PATH = '/rpc/2.0/nlp/v2/comment_tag';
|
const SENTIMENT_CLASSIFY_PATH = '/rpc/2.0/nlp/v1/sentiment_classify';
|
|
|
/**
|
* AipNlp类
|
*
|
* @class
|
* @extends BaseClient
|
* @constructor
|
* @param {string} appid appid.
|
* @param {string} ak access key.
|
* @param {string} sk security key.
|
*/
|
class AipNlp extends BaseClient {
|
constructor(appId, ak, sk) {
|
super(appId, ak, sk);
|
}
|
commonImpl(param) {
|
let httpClient = new HttpClient();
|
let apiUrl = param.targetPath;
|
delete param.targetPath;
|
let requestInfo = new RequestInfo(apiUrl,
|
param, METHOD_POST);
|
return this.doRequest(requestInfo, httpClient);
|
}
|
|
/**
|
* 词法分析接口
|
*
|
* @param {string} text - 待分析文本（目前仅支持GBK编码），长度不超过65536字节
|
* @param {Object} options - 可选参数对象，key: value都为string类型
|
* @description options - options列表:
|
* @return {Promise} - 标准Promise对象
|
*/
|
lexer(text, options) {
|
let param = {
|
text: text,
|
targetPath: LEXER_PATH
|
};
|
return this.commonImpl(objectTools.merge(param, options));
|
}
|
|
/**
|
* 词法分析（定制版）接口
|
*
|
* @param {string} text - 待分析文本（目前仅支持GBK编码），长度不超过65536字节
|
* @param {Object} options - 可选参数对象，key: value都为string类型
|
* @description options - options列表:
|
* @return {Promise} - 标准Promise对象
|
*/
|
lexerCustom(text, options) {
|
let param = {
|
text: text,
|
targetPath: LEXER_CUSTOM_PATH
|
};
|
return this.commonImpl(objectTools.merge(param, options));
|
}
|
|
/**
|
* 依存句法分析接口
|
*
|
* @param {string} text - 待分析文本（目前仅支持GBK编码），长度不超过256字节
|
* @param {Object} options - 可选参数对象，key: value都为string类型
|
* @description options - options列表:
|
* mode 模型选择。默认值为0，可选值mode=0（对应web模型）；mode=1（对应query模型）
|
* @return {Promise} - 标准Promise对象
|
*/
|
depparser(text, options) {
|
let param = {
|
text: text,
|
targetPath: DEP_PARSER_PATH
|
};
|
return this.commonImpl(objectTools.merge(param, options));
|
}
|
|
/**
|
* 词向量表示接口
|
*
|
* @param {string} word - 文本内容（GBK编码），最大64字节
|
* @param {Object} options - 可选参数对象，key: value都为string类型
|
* @description options - options列表:
|
* @return {Promise} - 标准Promise对象
|
*/
|
wordembedding(word, options) {
|
let param = {
|
word: word,
|
targetPath: WORD_EMBEDDING_PATH
|
};
|
return this.commonImpl(objectTools.merge(param, options));
|
}
|
|
/**
|
* DNN语言模型接口
|
*
|
* @param {string} text - 文本内容（GBK编码），最大512字节，不需要切词
|
* @param {Object} options - 可选参数对象，key: value都为string类型
|
* @description options - options列表:
|
* @return {Promise} - 标准Promise对象
|
*/
|
dnnlmCn(text, options) {
|
let param = {
|
text: text,
|
targetPath: DNNLM_CN_PATH
|
};
|
return this.commonImpl(objectTools.merge(param, options));
|
}
|
|
/**
|
* 词义相似度接口
|
*
|
* @param {string} word1 - 词1（GBK编码），最大64字节
|
* @param {string} word2 - 词1（GBK编码），最大64字节
|
* @param {Object} options - 可选参数对象，key: value都为string类型
|
* @description options - options列表:
|
* mode 预留字段，可选择不同的词义相似度模型。默认值为0，目前仅支持mode=0
|
* @return {Promise} - 标准Promise对象
|
*/
|
wordSimEmbedding(word1, word2, options) {
|
let param = {
|
word_1: word1,
|
word_2: word2,
|
targetPath: WORD_SIM_EMBEDDING_PATH
|
};
|
return this.commonImpl(objectTools.merge(param, options));
|
}
|
|
/**
|
* 短文本相似度接口
|
*
|
* @param {string} text1 - 待比较文本1（GBK编码），最大512字节
|
* @param {string} text2 - 待比较文本2（GBK编码），最大512字节
|
* @param {Object} options - 可选参数对象，key: value都为string类型
|
* @description options - options列表:
|
* model 默认为"BOW"，可选"BOW"、"CNN"与"GRNN"
|
* @return {Promise} - 标准Promise对象
|
*/
|
simnet(text1, text2, options) {
|
let param = {
|
text_1: text1,
|
text_2: text2,
|
targetPath: SIMNET_PATH
|
};
|
return this.commonImpl(objectTools.merge(param, options));
|
}
|
|
/**
|
* 评论观点抽取接口
|
*
|
* @param {string} text - 评论内容（GBK编码），最大10240字节
|
* @param {Object} options - 可选参数对象，key: value都为string类型
|
* @description options - options列表:
|
* type 评论行业类型，默认为4（餐饮美食）
|
* @return {Promise} - 标准Promise对象
|
*/
|
commentTag(text, options) {
|
let param = {
|
text: text,
|
targetPath: COMMENT_TAG_PATH
|
};
|
return this.commonImpl(objectTools.merge(param, options));
|
}
|
|
/**
|
* 情感倾向分析接口
|
*
|
* @param {string} text - 文本内容（GBK编码），最大102400字节
|
* @param {Object} options - 可选参数对象，key: value都为string类型
|
* @description options - options列表:
|
* @return {Promise} - 标准Promise对象
|
*/
|
sentimentClassify(text, options) {
|
let param = {
|
text: text,
|
targetPath: SENTIMENT_CLASSIFY_PATH
|
};
|
return this.commonImpl(objectTools.merge(param, options));
|
}
|
}
|
|
module.exports = AipNlp;
|
